%0 Journal Article %1 citeulike:10560379 %A Liu, Yiqun %A Chen, Fei %A Kong, Weize %A Yu, Huijia %A Zhang, Min %A Ma, Shaoping %A Ru, Liyun %C New York, NY, USA %D 2012 %I ACM %J ACM Trans. Web %K crowdsourcing social-web spam %N 1 %R 10.1145/2109205.2109207 %T Identifying Web Spam with the Wisdom of the Crowds %U http://dx.doi.org/10.1145/2109205.2109207 %V 6 %X Combating Web spam has become one of the top challenges for Web search engines. State-of-the-art spam-detection techniques are usually designed for specific, known types of Web spam and are incapable of dealing with newly appearing spam types efficiently. With user-behavior analyses from Web access logs, a spam page-detection algorithm is proposed based on a learning scheme. The main contributions are the following. (1) User-visiting patterns of spam pages are studied, and a number of user-behavior features are proposed for separating Web spam pages from ordinary pages. (2) A novel spam-detection framework is proposed that can detect various kinds of Web spam, including newly appearing ones, with the help of the user-behavior analysis. Experiments on large-scale practical Web access log data show the effectiveness of the proposed features and the detection framework.

@article{citeulike:10560379, abstract = {{Combating Web spam has become one of the top challenges for Web search engines. State-of-the-art spam-detection techniques are usually designed for specific, known types of Web spam and are incapable of dealing with newly appearing spam types efficiently. With user-behavior analyses from Web access logs, a spam page-detection algorithm is proposed based on a learning scheme. The main contributions are the following. (1) User-visiting patterns of spam pages are studied, and a number of user-behavior features are proposed for separating Web spam pages from ordinary pages. (2) A novel spam-detection framework is proposed that can detect various kinds of Web spam, including newly appearing ones, with the help of the user-behavior analysis. Experiments on large-scale practical Web access log data show the effectiveness of the proposed features and the detection framework.}}, added-at = {2017-11-15T17:02:25.000+0100}, address = {New York, NY, USA}, author = {Liu, Yiqun and Chen, Fei and Kong, Weize and Yu, Huijia and Zhang, Min and Ma, Shaoping and Ru, Liyun}, biburl = {https://www.bibsonomy.org/bibtex/2cb1e6be0b8ee5bb264819e0194fc795d/brusilovsky}, citeulike-article-id = {10560379}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2109207}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/2109205.2109207}, doi = {10.1145/2109205.2109207}, interhash = {2267cef4bce5693b9452fffa629b871a}, intrahash = {cb1e6be0b8ee5bb264819e0194fc795d}, issn = {1559-1131}, journal = {ACM Trans. Web}, keywords = {crowdsourcing social-web spam}, month = mar, number = 1, posted-at = {2012-04-12 19:07:53}, priority = {2}, publisher = {ACM}, timestamp = {2020-06-30T16:15:02.000+0200}, title = {{Identifying Web Spam with the Wisdom of the Crowds}}, url = {http://dx.doi.org/10.1145/2109205.2109207}, volume = 6, year = 2012 }